huggingface/diffusers

Project overview

Diffusers provides modular inference pipelines, interchangeable schedulers, and pretrained building-block models for diffusion-based image, audio, and video generation in PyTorch. It is intended for developers and researchers who need to run or customize diffusion systems via a Python library.

Project type

Model Development · Image & Vision · Video · Audio & Speech

Use cases

Image Processing

Deployment

Library integration

License

Apache-2.0

Best for

• Developers and researchers working in PyTorch who need to run, optimize, or customize state-of-the-art diffusion models for image, audio, and video generation.

Key capabilities

• Provides state-of-the-art diffusion pipelines that can be run in inference with just a few lines of code.
• Offers interchangeable noise schedulers for managing different diffusion speeds and output quality.
• Delivers pretrained models that can be used as building blocks for creating custom end-to-end diffusion systems.
• Provides guides and functionality for training diffusion models for different tasks with different training techniques.
• Includes functionality and guides to optimize diffusion models to run faster and consume less memory.

Limitations and risks

• The library relies on PyTorch as its primary deep learning framework, limiting use in non-PyTorch environments.

Getting started

• Install the package via pip or conda (such as pip install diffusers[torch]), load a pretrained model from the Hub, and generate an image in Python.

Evidence and sources

• GitHub project description: 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
• README: 🤗 Diffusers offers three core components: - State-of-the-art diffusion pipelines that can be run in inference with just a few lines of code. - Interchangeable noise schedulers for…
• README: 🤗 Diffusers is the go-to library for state-of-the-art pretrained diffusion models
• README: Guides for how to train a diffusion model for different tasks with different training techniques.
• Release: Diffusers 0.39.0: New image and video pipelines, core library improvements, and more

Reviewed at: 2026-07-17T09:13:15Z